MORSE: Semantic-ally Drive-n MORpheme SEgment-er
Computation and Language
2017-05-02 v3
Abstract
We present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes. This framework is the first to consider vocabulary-wide syntactico-semantic information for this task. We also analyze the deficiencies of available benchmarking datasets and introduce our own dataset that was created on the basis of compositionality. We validate our algorithm across datasets and present state-of-the-art results.
Cite
@article{arxiv.1702.02212,
title = {MORSE: Semantic-ally Drive-n MORpheme SEgment-er},
author = {Tarek Sakakini and Suma Bhat and Pramod Viswanath},
journal= {arXiv preprint arXiv:1702.02212},
year = {2017}
}